All Skills

Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

Manage Apple Reminders via remindctl CLI (list, add, complete, delete).

Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

Provides expert guidance on PyTorch Fully Sharded Data Parallel (FSDP) training, covering parameter sharding, mixed precision, CPU offloading, and FSDP2.

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a live Jupyter kernel. No new tools required.

Systematic multi-phase codebase audit for technical debt, architecture mapping, and defect detection. Read-only scanning before any modifications. Supports Vue/uni-app, JS/TS projects.

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

MaxFuse parameter tuning when protein panel size changes (26 → 59+ markers)

Preventing Jupyter cell hangs with explicit CuPy GPU memory cleanup

v5.6.0 joint multi-TF model: single model per symbol with broadcast 1Hour context replaces dual 15Min/1Hour models. Trigger: (1) replacing weighted-voting model aggregation, (2) adding broadcast features to vectorized env, (3) limited training data + worried about overfitting from doubling obs_dim, (4) backtest builder mismatch with newer feature counts.

Save backtest results to SQLite database for comparison. Trigger when: (1) tracking backtest history, (2) comparing model performance, (3) querying best backtests.

Use when tuning RL reward function weights, fixing reward hacking, or addressing P&L gradient issues

Fix F821 undefined name errors for optional dependencies using TYPE_CHECKING

Audit Jupyter notebooks for hardcoded values that contradict configuration cells. Trigger when: (1) notebook behavior differs from documented settings, (2) updating notebook version, (3) finding inconsistent values across cells.

Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→5600.

Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.

Fixes common PyTorch bugs including percentile calculations, LayerNorm for Conv1d, and buffer edge cases in reinforcement learning and neural network code.

Exclude ALL dotted symbols from yfinance sector lookups and training. Trigger when: (1) yfinance errors on warrants/units/class shares, (2) training notebook fails on excluded symbol types, (3) adding new symbol exclusion patterns.

Broker position reconciliation pattern for live trading systems

Normalize long-form CODEX cycle folders to short form before notebooks run. Trigger: cyc001_reg001_*, hard-coded cyc paths breaking, staged CODEX raw data failing in Notebooks 1/2.

Review and apply GitHub Copilot suggestions on pull requests. Trigger when reviewing PRs with Copilot suggestions.

Derive selection thresholds from market data instead of hardcoding. Trigger when: (1) reviewing hardcoded parameters, (2) volume/price thresholds seem arbitrary, (3) selection returns too many/few candidates.

Dependency Safety Guards

Bulk-update stale workflow scripts across KINTSUGI projects. Trigger: scripts not propagating, QC failures, batch stalls after code updates.

Use when implementing risk-adjusted rewards, discussing Sharpe ratio in RL training, or tuning reward components for risk awareness

Symbol Database Selection Pattern

Populate symbol database with crypto symbols before training. Trigger when: (1) live trader fails with 'CRYPTO VIOLATION', (2) no crypto models in models/rl_symbols/, (3) db.get_candidates(asset_types=['crypto']) returns 0, (4) starting fresh training without crypto.

Use the Gemini CLI for one-shot Q&A, summarization, and generation tasks. Trigger when Gemini-specific CLI usage, model selection, or JSON-formatted output is needed.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.